• The Transactions of the Korea Information Processing Society
• /
• v.1 no.4
• /
• pp.541-550
• /
• 1994

A true color image is needed many data on the occasion of the transmission and storage. Therefore, we want to describe color image by a minority data without unreasonableness at eyesight. In this paper, it is presented 256 colormap construction method in RGB, YIQ/YUV space and common colormap expression method at merge between colormaps by reason of dissimilar original color image to display at a monitor for each other colormap at the same time. In comparison with processed result in RGB, YIQ/YUV space, it was measured by PSNR, standard variation, and edge preservation rate using sobel operator. Process time is 3second in colormap construction and 2second in merge between colormaps. In the PSNR value, RGB space has higher 0.15, 0.34 on an average than YIQ and YUV spae. Standard variation has lower in 0.15, 0.41 on an average than Yiq and YUV space. But in the data compression, YIQ/YUV space have about 1/3 compression efficiency than RGB space by reason of use to only 4bit of 8bit in color component.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.5
• /
• pp.193-202
• /
• 2004

This paper presents a novel histogram and color information based algorithm for detecting and tracking multiple pedestrians from a moving camera. In the proposed method, RGB color histogram is used to detect adjacent pedestrians and RGB mean value is used to track detected pedestrians. Therefore, our algorithm detect contiguous or a few occluded pedestrians and track in case pedestrian's shape change. The experimental results on our test sequences demonstrate the high efficiency of our method.

• Journal of Korea Society of Industrial Information Systems
• /
• v.10 no.2
• /
• pp.102-108
• /
• 2005

CIELAB coordinate is represented by one lightness component and two chromaticity components and similar to human visual system. Visual devices such as computer monitor display images using RGB coordinate. We propose a technique for inserting the watermark of visually recognizable mark into the middle frequency domain of image. RGB coordinate image is transformed into CIELAB coordinate, which include the characteristics of Human vision and then a* component is transformed into DFT(Discrete Fourier transform) transform.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.949-951
• /
• 2005

카메라를 이용하여 영상을 인식할 때 이진화의 과정을 거쳐 배경과 원하는 물체사이의 분리를 해주어야 한다. 하지만, 입력되어진 컬러 영상에서 집중 조명 혹은 주변 환경에 의해 영상이 그라데이션 되어질 경우 픽셀의 정확한 컬러를 인식하기 곤란해지며 이진화의 어려움을 겪게 된다. 본 연구에서는 이러한 집중 조명과 그라데이션의 영향을 받지 않고 이진화 수행을 가능토록 하는 새로운 방법을 제안한다. 영상의 픽셀은 RGB 채널간의 고유한 비율을 유지하고 있다. 조명의 영향을 받게 될 경우 하나의 색을 가진 픽셀은 조명의 밝기에 의해 픽셀값이 증가 혹은 감소하게 된다. 따라서, 컬러의 픽셀을 분석하여 해당하는 컬러의 표준 RGB값으로 변화하여 줄 경우 영상내의 픽셀의 컬러 분포는 한정된 범위로 좁혀져 히스토그램을 단순하게 표현 할 수 있으며 집중조명과 그라데이션의 영향을 받은 컬러 영상도 효율적으로 이진화를 할 수 있게 된다.

• The KIPS Transactions:PartB
• /
• v.9B no.1
• /
• pp.129-138
• /
• 2002

In this paper, a distance measuring algorithm for motion capture using color stereo camera is proposed. The color markers attached on articulations of an actor are captured by stereo color video cameras, and color region which has the same color of the marker's color in the captured images is separated from the other colors by finding dominant wavelength of colors. Color data in RGB (red, green, blue) color space is converted into CIE (Commission Internationale del'Eclairage) color space for the purpose of calculating wavelength. The dominant wavelength is selected from histogram of the neighbor wavelengths. The motion of the character in the cyber space is controlled by a program using the distance information of the moving markers.

• The KIPS Transactions:PartB
• /
• v.11B no.3
• /
• pp.317-326
• /
• 2004

This paper presents a new method for the detection of multiple pedestrians and tracking of a specific pedestrian using color information from a moving camera. We first extract motion vector on the input image using BMA. Next, a difference image is calculated on the basis of the motion vector. The difference image is converted to a binary image. The binary image has an unnecessary noise. So, it is removed by means of the proposed noise deletion method. Then, we detect pedestrians through the projection algorithm. But, if pedestrians are very adjacent to each other, we separate them using RGB color information. And we track a specific pedestrian using RGB color information in center region of it. The experimental results on our test sequences demonstrated the high efficiency of our approach as it had shown detection success ratio of 97％ and detection failure ratio of 3％ and excellent tracking.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.151-154
• /
• 2001

본 논문의 목적은 범용 USB 카메라 입력 영상으로부터 실시간으로 얼굴을 추적하는 시스템을 구현하는데 있다. 먼저 USB 카메라로부터 영상을 입력받은 후 2차원 RGB 컬러 모델링으로 추출한 살색 영역을 찾고 가로, 세로 프로젝선 정보를 이용하여 얼굴을 찾는다. 기존의 RGB 컬러 모델을 개선하여 빛에 강인한 모델링을 하였으며, 프로젝션 정보를 이용할 때 일어나는 에러를 최소화하기 위하여 누적 히스토그램 영역 결합 알고리즘을 제안하였다. 구현한 시스템은 움직임이 많은 영상에도 빠른 속도를 보였으며, 특히 영상의 움직임이적은 경우 카메라에서 영상을 보여 주는 것과 동시에 얼굴을 찾아내어, 연속적인 프레임을 처리할 수 있는 성능을 보였다.

• Journal of Intelligence and Information Systems
• /
• v.8 no.1
• /
• pp.87-101
• /
• 2002

In this paper, we proposes the car plate recognition and describe the parking control system using the proposed car plate recognition algorithm. The car plate recognition system using color information and fuzzy c-means algorithm consists of the extraction part of a car plate from a car image and the recognition part of characters in the extracted car plate. This paper eliminates green noise from car image using the mode smoothing and extract plate region using green and white information of RGB color. The codes of extracted plate region is extracted by histogram based approach method and is recognized by fuzzy c-means algorithm. For experimental, we tested 80 car images. We shows that the proposed extraction method is better than that from the color information of RGB and HSI, respectively. So, we can know that the proposed car plate recognition method using fuzzy c-means algorithm was very efficient. We develop the parking control system using the proposed car plate recognition method, which showed performance improvement by the experimental results.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2005.05a
• /
• pp.273-278
• /
• 2005

전정색영상과 달리 컬러영상에서 개체를 추출할 경우 밴드별 분광특성을 이용하여 특정지물을 효과적으로 인식할 수 일고 밝기값만으로 구별해낼 수 없는 개체를 추출할 수 있는 장점이 있다. 본 연구에서는 컬러영상에서 지형지물을 추출하기 위해 컬러정보를 이용하여 경계를 추출하는 연구를 수행하기 위해 일반적으로 사용하는 RGB 색체계가 아닌 CIEL*Ch 색체계로 변환한 후 L*에서 경계를 추출하고 C, h값으로 특정지물을경계를 추출하는 기법으로 컬러영상의 경계를 추출하였다.

• The KIPS Transactions:PartB
• /
• v.15B no.3
• /
• pp.229-236
• /
• 2008

This paper examines effectiveness of using color images instead of grayscale ones for automatic lipreading. First, we show the effect of color information for performance of humans' lipreading. Then, we compare the performance of automatic lipreading using features obtained by applying principal component analysis to grayscale and color images. From the experiments for various color representations, it is shown that color information is useful for improving performance of automatic lipreading; the best performance is obtained by using the RGB color components, where the average relative error reductions for clean and noisy conditions are 4.7% and 13.0%, respectively.